Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code includes and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न्ने
    0.36
    umed
    0.36
    Vir
    0.36
    olica
    0.36
    ştik
    0.36
    gkin
    0.36
    rowski
    0.35
     barred
    0.35
    UTES
    0.35
     Kochubei
    0.34
    POSITIVE LOGITS
    Routes
    0.38
     Resource
    0.36
    Resource
    0.36
     Richtung
    0.36
     Sails
    0.36
     Ass
    0.35
     Assets
    0.35
    Directions
    0.35
     Routes
    0.35
    floor
    0.34
    Act Density 0.015%

    No Known Activations